Related Experiment Video
Updated: Jan 11, 2026
09:16
Multi-Modal Signals for Analyzing Pain Responses to Thermal and Electrical Stimuli
Published on: April 5, 2019
11.4K
Identifying Suicidal Ideation in Older Patients With Chronic Pain Using Explainable Machine Learning: A
Xiaoang Zhang1,2, Weichen Liu1,2, Daying Zhang2
1School of Nursing, Jiangxi Medical College, Nanchang University, China.
Western Journal of Nursing Research
|November 11, 2025
Summary
Machine learning models can identify suicidal ideation (SI) risk in older adults with chronic pain. Key factors include pain level, social support, and pain catastrophizing, aiding early detection and intervention.
Area of Science:
- Gerontology
- Psychiatry
- Data Science
Background:
- Early identification of suicidal ideation (SI) in older adults with chronic pain is crucial.
- Limited methods exist for SI risk identification and stratification in this population.
- Machine learning offers a valuable approach to analyze complex risk factor relationships.
Purpose of the Study:
- To develop explainable machine learning models for identifying SI risk in older adults experiencing chronic pain.
Main Methods:
- A cross-sectional study of 516 older adults with chronic pain in China.
- Data preprocessing included Min-Max Normalization and SMOTETomek.
- Machine learning models were developed and interpreted using Shapley Additive Explanations.
Main Results:
- Several factors were associated with SI, including pain characteristics and social support.
- The Random Forest model achieved high accuracy (0.85) and AUC (0.89).
- Pain level, perceived social support, and pain catastrophizing were the most influential risk factors.
Conclusions:
- Explainable machine learning models aid in early SI detection and risk stratification for nurses.
- Identified key risk factors support targeted interventions and clinical screening for SI in older adults with chronic pain.
